글

WarpQuant: Dual-Domain Low-Bit LLM QuantizationEnglish
A post-training quantization method that reaches INT2/INT3 SOTA accuracy and runs the compressed weights directly through a C++/CUDA llama.cpp kernel — 7.36× faster decoding than GPTQ W3.
2026.08.162분quantization cuda llm 🛠
Building a Production LangGraph Travel AgentEnglish
How I built a LangGraph travel assistant that searches flights, hotels, and activities in parallel and assembles budget-aware packages.
2025.11.1222분llm agents langgraph 🛠≥20min
Modern Anti-Bot Systems and How to Bypass ThemEnglish
An engineering deep-dive into web scraping in 2025, with a production case study.
2025.11.0911분web-scraping anti-bot playwright 🛠